@Article{jihpp.2020.016299,
AUTHOR = {Qianqian Li, Meng Li, Lei Guo, Zhen Zhang},
TITLE = {Random Forests Algorithm Based Duplicate Detection in On-Site  Programming Big Data Environment},
JOURNAL = {Journal of Information Hiding and Privacy Protection},
VOLUME = {2},
YEAR = {2020},
NUMBER = {4},
PAGES = {199--205},
URL = {http://www.techscience.com/jihpp/v2n4/41151},
ISSN = {2637-4226},
ABSTRACT = {On-site programming big data refers to the massive data generated in the 
process of software development with the characteristics of real-time, complexity 
and high-difficulty for processing. Therefore, data cleaning is essential for on-site 
programming big data. Duplicate data detection is an important step in data 
cleaning, which can save storage resources and enhance data consistency. Due to 
the insufficiency in traditional Sorted Neighborhood Method (SNM) and the 
difficulty of high-dimensional data detection, an optimized algorithm based on 
random forests with the dynamic and adaptive window size is proposed. The 
efficiency of the algorithm can be elevated by improving the method of the keyselection, reducing dimension of data set and using an adaptive variable size 
sliding window. Experimental results show that the improved SNM algorithm 
exhibits better performance and achieve higher accuracy.},
DOI = {10.32604/jihpp.2020.016299}
}